相关论文: MATEO: A Multimodal Benchmark for Temporal Reasoni…

In this paper, we present NEMO, a system that translates Natural-language descriptions of decision problems into formal Executable Mathematical Optimization implementations, operating collaboratively with users or autonomously. Existing…

Effective asynchronous planning, or the ability to efficiently reason and plan over states and actions that must happen in parallel or sequentially, is essential for agents that must account for time delays, reason over diverse long-horizon…

Sequential decision-making in high-dimensional continuous action spaces, particularly in stochastic environments, faces significant computational challenges. We explore this challenge in the traditional offline RL setting, where an agent…

Large language models (LLMs) demonstrate impressive performance on a wide variety of tasks, but they often struggle with tasks that require multi-step reasoning or goal-directed planning. Both cognitive neuroscience and reinforcement…

Large Language Models (LLMs) have recently been extended to the video domain, enabling sophisticated video-language understanding. However, existing Video LLMs often exhibit limitations in fine-grained temporal reasoning, restricting their…

Large Language Models (LLMs) in agentic workflows combine multi-step reasoning, heterogeneous tool use, and collaboration across multiple specialized agents. Existing LLM serving engines optimize individual calls in isolation, while…

Developing autonomous agents for web-based tasks is a core challenge in AI. While Large Language Model (LLM) agents can interpret complex user requests, they often operate as black boxes, making it difficult to diagnose why they fail or how…

Large language model (LLM) based task plans and corresponding human demonstrations for embodied AI may be noisy, with unnecessary actions, redundant navigation, and logical errors that reduce policy quality. We propose an iterative…

In this paper, we introduce MIO, a novel foundation model built on multimodal tokens, capable of understanding and generating speech, text, images, and videos in an end-to-end, autoregressive manner. While the emergence of large language…

Aligning large language models (LLMs) with diverse and multifaceted user preferences is a fundamental challenge in personalized AI systems. Existing multi-objective alignment methods either rely on costly training or require pre-trained…

Modern large language models (LLMs) increasingly rely on inference-time planning and external tools to improve reasoning. We benchmark this behavior on two real-world settings: event-centric question answering over graph-structured…

Recent progress in large language models (LLMs) has enabled tool-augmented agents capable of solving complex real-world tasks through step-by-step reasoning. However, existing evaluations often focus on general-purpose or multimodal…

Task planning is an important component of traditional robotics systems enabling robots to compose fine grained skills to perform more complex tasks. Recent work building systems for translating natural language to executable actions for…

Large Language Models (LLMs) have achieved remarkable success across a wide range of tasks, but serving them efficiently at scale remains a critical challenge due to their substantial computational and latency demands. While most existing…

Temporal reasoning in multi-session dialogues presents a significant challenge which has been under-studied in previous temporal reasoning benchmarks. To bridge this gap, we propose a new evaluation task for temporal reasoning in…

Multimodal large language models (MLLMs) have achieved impressive progress on vision language benchmarks, yet their capacity for visual cognitive and visuospatial reasoning remains less understood. We introduce "Mind's Eye", a…

The rapid advancement of Large Language Models (LLMs) has sparked growing interest in their application to time series analysis tasks. However, their ability to perform complex reasoning over temporal data in real-world application domains…

Recent research has shown that LLM performance on reasoning tasks can be enhanced by scaling test-time compute. One promising approach, particularly with decomposable problems, involves arranging intermediate solutions as a graph on which…

Achieving expert-level performance in simulation-based training relies on the creation of complex, adaptable scenarios, a traditionally laborious and resource intensive process. Although prior research explored scenario generation for…

Agentic AI enables LLM to dynamically reason, plan, and interact with tools to solve complex tasks. However, agentic workflows often require many iterative reasoning steps and tool invocations, leading to significant operational expense,…